skill-budget-audit SKILL.md skillA
skill-budget-audit from oleg-koval/agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add oleg-koval/agent-skills/skill-budget-audit@git:20260828.aaaffd4Pins git:20260828.aaaffd4 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- oleg-koval/agent-skills
- Path
adapters/grok/olko-skill-meta/skills/skill-budget-audit/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260828.aaaffd4, committed Aug 28, 2026
- First version recorded
- Aug 24, 2026
- Size
- 5,131 bytes
- Repository stars
- 3
- License
- MIT
Diagnose and fix Claude Code's skill context budget overflow, identify heavy plugin bundles that exceed the 2% budget, remove domain-specific ones, deactivate rarely-used skill sets, and validate the warning clears. Use when Claude Code shows "Exceeded skills context budget" or skill descriptions are stripped.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
<!-- Generated by scripts/build-adapters.sh. Do not edit directly. --> > 🤖 *Auto-generated by **weekly-pattern-learner** · Skill context budget overflow appeared in 2 sessions this week (Jun 2026): initial investigation (7 turns, 742 skills hidden) and cleanup followup (14 turns)* # Skill Context Budget Audit ## Overview Claude Code allocates 2% of its context window for skill descriptions. With too many plugins installed, descriptions get stripped and skills become invisible. This skill audits plugin bundles, removes unused domain-specific ones, and restores skill discoverability. ## When to Use - Claude Code shows: `⚠ Exceeded skills context budget of 2%. All skill descriptions were removed and N additional skills hidden.` - Skill invocations fail silently or Claude cannot find a skill by name - After installing multiple plugin bundles, noticing slowdown or skill lookup failures - Periodically as a maintenance step when adding new skill collections ## Workflow ### 1. Confirm the Symptom ```bash # Check Claude Code logs for context budget warning cat ~/.claude/logs/claude-code.log 2>/dev/null | grep -i "skill" | tail -20 # Or count installed plugins …
Read the whole file at its exact version.
How to install
mdr add oleg-koval/agent-skills/skill-budget-audit@sha256:f701432ea1522cb4The line at the top of this page pins the label git:20260828.aaaffd4, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_ajl66jxx6ms2xeev)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Aug 24, 2026 and Aug 28, 2026, about one every 3 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260828.aaaffd4 latest | 2026-08-28 | aaaffd4 | 5,131 B | A | view · diff |
| git:20260824.c71bceb | 2026-08-24 | c71bceb | 5,137 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (5131 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
oleg-koval/agent-skills · 3 stars · license MIT · pushed 2026-10-21 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ajl66jxx6ms2xeev GET https://markdownregistry.com/api/v1/resolve?ref=oleg-koval/agent-skills/skill-budget-audit GET https://markdownregistry.com/api/v1/blob/f701432ea1522cb4b6dac49ef739c1bbe171c58962f6db8982f5cdb15d0a9cfd
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from oleg-koval/agent-skills
Every file in oleg-koval/agent-skills